TY - GEN
A1 - Bilski, Jarosław
A2 - Korbicz, Józef - red.
A2 - Uciński, Dariusz - red.
PB - Zielona Góra: Uniwersytet Zielonogórski
N2 - A new algorithm for training feedforward multilayer neural networks is proposed. It is based on recursive least squares procedures and U-D factorization, which is a well-known technique in filter theory. It will be shown that due to the U-D factorization method, our algorithm requires fewer computations than the classical RLS applied to feedforward multilayer neural network training.
L1 - http://www.zbc.uz.zgora.pl/Content/57500/AMCS_2005_15_1_9.pdf
L2 - http://www.zbc.uz.zgora.pl/Content/57500
KW - neural networks
KW - learning algorithms
KW - recursive least squares method
KW - UD factorization
T1 - The UD RLS algorithm for training feedforward neural networks
UR - http://www.zbc.uz.zgora.pl/dlibra/docmetadata?id=57500
ER -